CN102496280A - Method for obtaining road condition information in real time - Google Patents
Method for obtaining road condition information in real time Download PDFInfo
- Publication number
- CN102496280A CN102496280A CN201110412993XA CN201110412993A CN102496280A CN 102496280 A CN102496280 A CN 102496280A CN 201110412993X A CN201110412993X A CN 201110412993XA CN 201110412993 A CN201110412993 A CN 201110412993A CN 102496280 A CN102496280 A CN 102496280A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic information
- road
- mobile phone
- switching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for obtaining road condition information in real time, which belongs to the field of intelligent transportation and includes deleting wireless mobile data not meeting the requirements of road condition information calculation, performing path speculation, judging validity of calculation on road chain travel time by the wireless mobile data according to travel paths and classified characteristic value obtained through path speculation, and integrating valid data to obtain road condition information. The method uses the existing wireless communication network control signals for demarcating travel tracks of vehicle-mounted cell phones so as to calculate road condition information. Due to the fact that the wireless positioning technology based on the network makes the best of the existing mobile communication facilities and network resources, all-weather road real-time transportation information collection covering all road nets can be achieved with small investment, and therefore the road condition information calculation technology based on wireless network control signals can meet the requirements of real-time road condition calculation in vast areas.
Description
Technical field
The present invention relates to intelligent transportation field, particularly a kind of traffic information real time acquiring method that switches locator data based on the base station.
Background technology
Development along with social economy and communication; Problems such as road passage capability congested in traffic and that traffic hazard causes reduces, road speed descends, traffic delay increases, fuel consumption increases, environmental pollution increases the weight of more and more show especially out, become the common difficult problem of paying close attention in the whole world.In recent years, many countries drop into a large amount of manpower and materials and carry out the management of road traffic transportation system and the exploitation of control technology, are devoted to the various new and high technologies of integrated use systematically to solve the road traffic problem.In the case; Intelligent transportation system (Intelligent Transportation System; ITS) arise at the historic moment; The advanced traffic control system of its core subsystem (Advanced Traffic Management System, ATMS) (Advanced Traffic Information System promptly is to apply in whole traffic administration and the service technological means such as magnanimity information processing, data communication, electronic sensor and Electronic Control are integrated ATIS) with advanced transportation information service systems; Provide a kind of on a large scale in, comprehensive play a role; In real time, comprehensive traffic information service accurately and efficiently, reach and practice thrift traveler hourage, alleviate congestion in road, reduce purposes such as polluting, save the energy.
The traffic information collection technology that generally adopts in the world at present mainly is fixed traffic information collection technology and movable traffic information acquisition technique.Fixed traffic information collection technology is at main roads and critical junction the traffic data that electronic equipments such as loop sensor, microwave monitor are monitored certain cross-section of specific road section on the road network to be installed: vehicle flowrate, occupancy etc.; And then the average speed of acquisition vehicle; Information such as the traffic congestion situation of road need adopt the complicated algorithm estimation to obtain but obtain these data.The advantage of these equipment is comparatively accurate to the measurement of traffic flow, and shortcoming is that deployed with devices and maintenance cost are high, therefore, generally only is deployed on the main roads of city, and coverage rate is low.The movable traffic information acquisition technique as the bus or the taxi of GPS vehicle positioning device are installed, regularly returns information such as its position, speed, travel direction through mobile device, and then obtains the relevant traffic information of vehicle ' road.Traditional portable acquisition mode requires the positioning of mobile equipment precision higher, and receives collecting device self form feature affects bigger, fixes like the bus running circuit, and the taxi driving range is limited etc.
Because the original traffic data of intelligent transportation system is mainly derived from the Floating Car in the city, this has just caused the scope of its covering and service mainly to concentrate on the city.And to obtain the traffic data in suburb and villages and small towns, and mainly depend on the toroid winding data acquisition technology at present, promptly gather traffic data through on highway, burying toroidal mode underground.The problem of this acquisition mode is: burying coil underground can damage building road; The coil spoilage is high, maintenance cost is bigger, and according to DOT's door measuring and calculating, the coil spoilage is approximately 30%, needs every year cost to safeguard for about 20～3,000,000,000 dollars; The place speed of a motor vehicle and data on flows can only be collected, Link Travel Time can not be obtained; Limited coverage area only could image data in the highway section of burying the coil facility underground.Because these toroidal intrinsic problems, it is not extensive to cause utilizing its mode of gathering traffic data to be used, and intelligent transportation system is still less in the coverage in suburb and villages and small towns.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of traffic information real time acquiring method, be used to improve the covering service range of intelligent transportation system.
Embodiments of the invention provide a kind of traffic information real time acquiring method, comprising:
The radio data that traffic information calculates is not satisfied in deletion; Carry out path culculating, the driving path and the characteristic of division value that obtain according to path culculating are judged the validity of satisfying the need radio data chain calculating hourage; Valid data are merged, obtain traffic information.
The present invention uses the driving trace that existing cordless communication network signaling is demarcated vehicle carried mobile phone, and then calculates traffic information.Because based on network wireless location technology makes full use of existing mobile communication facility and Internet resources; Can realize covering system-wide net, the collection of round-the-clock road Real-time Traffic Information with investment seldom, therefore the traffic information computing technique based on radio network signaling can satisfy the demand that wide regional real-time road calculates.
Description of drawings
Fig. 1 is based on mobile phone switching the carrying out Mobile Phone Locating mode synoptic diagram that road conditions are obtained in the embodiment of the invention;
Fig. 2 switches the process flow diagram of the traffic information real time acquiring method of locator data for what the embodiment of the invention provided based on the base station;
The method flow diagram that carries out path culculating that Fig. 3 provides for the embodiment of the invention;
The structural drawing of three layers of road net model that Fig. 4 provides for the embodiment of the invention;
The synoptic diagram that road net model is carried out gridding that Fig. 5 provides for the embodiment of the invention;
The method flow diagram that the traffic information that Fig. 6 provides for the embodiment of the invention merges.
Embodiment
For making the object of the invention, technical scheme and advantage clearer, the present invention is made further detailed description below in conjunction with accompanying drawing.
Present embodiment is used the driving trace that existing cordless communication network signaling is demarcated vehicle carried mobile phone, and then calculates traffic information.Because based on network wireless location technology makes full use of existing mobile communication facility and Internet resources; Can realize covering system-wide net, the collection of round-the-clock road Real-time Traffic Information with investment seldom, therefore the traffic information computing technique based on radio network signaling can satisfy the demand that wide regional real-time road calculates.The embodiment of the invention proposes wireless running fix data preprocessing method according to the radio data characteristics, rejects and does not satisfy the data that traffic information calculates; Switch the location characteristics to the base station, on traditional path culculating algorithm basis, proposed a kind of new routing strategy; Introducing distinguishes that based on the valid data of SVM model solves the insincere problem of information on the same road chain that routing strategy adjustment caused.
The radio data that present embodiment adopts is any active ues message registration data that operator provides, and any active ues refers to trigger the user of mobile communication incident (conversation, note sending and receiving etc.).Its data layout is as shown in the table, wherein the signaling event type comprise that switching on and shutting down, normal position are upgraded, paging is corresponding, short message receiving-transmitting, phone caller, sub-district switching etc.Wherein sub-district switching and normal position renewal (switch the base station in the conversation) can be used for generating switching sequence.
Table 1
In the present embodiment, in a processing cycle, any adjacent two switching points of same mobile phone are formed a switch unit.The set of the continuous raw readings of same mobile phone becomes a switching sequence, and a switching sequence comprises at least one switch unit.
Switch (Handover) and refer to that mobile phone is in the process that moves; Can keep continual with the base station and communicate by letter, when the signal strength weakening of mobile phone Current Serving BTS, the signal intensity of neighbor base station surpasses current base station; Mobile phone signal can switch to neighbor base station, so that obtain better signal.In the process of switching, operator can keep the relevant record that switches, and this is to utilize the mobile phone switching to carry out information acquisition required data are provided.The position that the mobile phone switching takes place is called switching point (Handover Point), and the highway section that recurs twice mobile phone switching is for switching the highway section, and switching point continuous on the road is formed road handover network (Handover Network) jointly with the switching highway section.Record mobile phone a series of switching point is confirmed the driving path of vehicle under the mobile phone through map match, accomplish route matching after, the average speed that carries out the highway section calculates.
Switch based on mobile phone that to carry out the Mobile Phone Locating mode that road conditions obtain as shown in Figure 1; The zone (switch area) that mobile phone switches for taking place in the honeycomb intersection region among the figure; When mobile phone gets into next base station by last base station through the switch area, can write down a switching time and switching point, same; When through next switch area, can write down next switching time and switching point.So just produced a mistiming, just can calculate the speed that mobile phone moves between two switching points according to the distance between the switch area.In this method of application, need repeatedly the switching point of the definite mobile phone of test and switch the highway section, calculate the road section length between adjacent two switching points.Utilize the mobile phone switching point to gather the method for transport information, need confirm handover network through repeatedly measuring, convenient further to the location of mobile phone.
Fig. 2 be the embodiment of the invention provide switch the process flow diagram of the traffic information real time acquiring method of locator data based on the base station, this method comprises:
The radio data that traffic information calculates is not satisfied in step 201, deletion.Because the data in mobile phone reliability based on wireless network signal is difficult to ensure, has abnormal data in a large number and can't satisfy the data that traffic information calculates, therefore carry out to carry out preliminary screening to data before traffic information calculates.
Available data is any active ues data records; Comprise mobile subscriber and non-moving user in any active ues; Comprise vehicle carried mobile phone user and non-vehicle carried mobile phone user among the mobile subscriber again; Because non-moving data and non-vehicle-mounted data can not be used to demarcate the road network Vehicle Speed, so data pre-service key problem is exactly these two types of data of tentatively rejecting in the data in mobile phone.Concrete screening technique is:
1, deletion invalid data: invalid radio data (invalid data) is tentatively deleted through parameters such as base station location, mobile phone state, record numbers.Invalid data is meant the user data that does not go in the processing cycle in the highway scope of suburbs or do not trigger the mobile communication incident.In the actual treatment; Should delete the radio data of the non-any active ues in the processing cycle according to mobile phone state; The base station location of affiliated base station does not cover the radio data of suburbs strategic road, and writes down the radio data that number is less than three mobile phone in a processing cycle.Deletion is less than the data in mobile phone of three records because every records a basic station number, and a switching confirmed in two records, twice switching takes place at least just can mate and calculate.
2, delete non-moving data: through non-moving data are deleted in the calculating of the effective switching times in base station in the processing cycle.The applicant is through finding that to the available data analysis switched and the identical radio data of base station shifting coordinate the base station during existence was conversed continuously, and such data are the abnormal data that Communication Jamming, data disappearance cause.Because the base station coordinates that effectively switching requires to switch writes down is different with the base station coordinates of its last record; The radio data of one mobile phone should satisfy handles cycle memory twice and above effective switching; Therefore, need delete the discontented invalid data that is enough to condition.
3, delete non-vehicle-mounted data: non-vehicle-mounted data is deleted in the judgement (whether exist and repeat to switch) through to the switching sequence characteristics.Repeat to switch in the base station switching sequence (base station that this mobile phone switched in the processing cycle) that is meant mobile phone wireless mobile data in the processing cycle and loop occurs.With sequence (X
1, X
2..., X
n) indicating the base station switching sequence, loop is meant and has an X
i, make X
1To X
I-1In exist one to equate at least with it.Loop occurs if handle in the cycle intra sequence (switching that this mobile phone took place) in the processing cycle, then reject this data in mobile phone.
The grid at place is switched in step 2021, location, and obtains all highway sections in this grid.Present embodiment adopts three layers of road net model, and as shown in Figure 4, road network structure is made up of node, highway section and three layers of notion of road chain.Simultaneously, the needs in order to locate have fast carried out gridding to road net model, and are as shown in Figure 5.So-called gridding is meant that between the 0.0025-0.005 degree, selecting a value is step-length (also can be made as other reasonable step-length according to real system), with road network from top to bottom, the even piecemeal of gridding from left to right; Suppose it is divided into M * N grid; (M * N), wherein M and N are respectively the number of lines and columns of piecemeal to brief note, and the line number of grid is from 0 to M-1 for Grid; Column number from 0 to N-1; Preserve the attribute of its minimum and maximum longitude and latitude, and all road section ID that write down that each grid comprises or intersect with grid four limits, with the direction attribute in grid and every highway section index as the candidate matches highway section as its four edges.
Step 2022, with adding in the chain set of search road less than 250 meters highway section with switching position distance in the grid.
Step 2023, judge whether next bar data in mobile phone record switches, if, then with two base station shifting mid points as mobile phone location, otherwise with base station location as mobile phone location.Because have multiple incident in the data in mobile phone record, have only the sub-district to switch to upgrade just can demarcate accurately and switch time and the position that takes place, so these two records to represent to switch with the normal position, other logouts can only be with base station location as mobile phone location.
Step 2024, in the set of search road chain, seek the coupling highway section.The coupling highway section of article one switching record is set to initial highway section in the switching sequence of mobile phone.The coupling highway section drop on this highway section for the mobile phone location projection or apart from this highway section less than 250m.If there is this coupling highway section of switching record, then will add the candidate road section collection from initial highway section to the set in the successful highway section of coupling; Otherwise,,, continue to seek the coupling highway section with adding in the chain set of search road with the highway section that links to each other in current highway section in the topological structure according to road network topology.Here said highway section all is meant ready-portioned highway section in the grid.
If two coupling highway sections of switching between the record surpass 30 in the switching sequence, then think and do not find the coupling highway section, from the chain set of search road, delete respective stretch; If chain set in road then stops search for empty in the search procedure, export current coupling highway section set.
Step 2025, calculating SVMs (Support Vector Machine, SVM) characteristic of division value.The follow-up judgement path culculating result validity of calculating chain hourage of satisfying the need that is calculated as of characteristic of division value provides the data support, and these eigenwerts are subsidiary calculating in the middle of map matching process.Path culculating cooperates with the identification of route availability of back and carries out, and when path culculating is exported many matching results, exports six category features for each matching result, and whether this result is effective to be used for follow-up judging.SVM is that the VC that is based upon statistical learning ties up on (VC dimension) theory and structural risk minimization (the structural risk minimization) principle basis.SVM obtains best popularization ability through nicety of grading (to the classification correctness of sample-specific) and classification capacity (arbitrary sample is carried out the inerrancy classification) are traded off in the hope of making sorter.Eigenwert is the abstractdesription to data as the input of svm classifier device, thus eigenwert choose extremely importantly, can reflect accurately and treat that the grouped data characteristics will directly influence final classifying quality.The characteristic of division that present embodiment is chosen comprises: data drift features, switching sequence integrity feature, timeliness characteristic, distance feature, event attribute characteristic and percentage speed variation characteristic.
Data drift in the present embodiment refers to exist in the switching sequence situation of continuous switching direction angle greater than 90 degree.Wherein switching direction is meant two vector that the base station is formed that switch; The base station sequence of even a certain switching is (Cell1; Cell2), switching direction sensing amount
direction then.The data drift features refers to the average drift angle value in the switching sequence.Formula is following:
Wherein DA is the average drift angle, DA
iThe switching sequence angle of respectively drifting about, DN is the number that drift takes place in the same switching sequence.
If vehicle goes according to certain track; Then its switching point should have good directivity; Find through analyzing data, most of in the invalid data data drift takes place, and according to the difference of drift angle; Influence degree is difference to some extent, therefore with the average drift angle of switching sequence as a characteristic of division.
Distance feature comprises operating range and road chain length ratio, switching point distance.Because distance is generally far away between the data in mobile phone switching point; When a switching interval is striden many road chains; Each road chain speed is the speed average between switching point, and generally, this average is influenced by long road chain more; In order to reflect the road chain length and to switch the influence relation of distance to information accuracy, with operating range and road chain length than with switching point apart from as two characteristic of divisions.
The switching sequence integrity feature shows as and is matched to power, promptly matees the ratio that accounts for the total number of records that successfully writes down in the switching sequence.
The timeliness characteristic comprises switching interval, switches the record number.Logarithm finds according to observations, and when less or time interval was longer when switching sequence record number, the road chain travel speed error of calculation was bigger, therefore chooses switching interval and switches the record number as characteristic of division.
The event attribute characteristic is that whether the incident in the initial termination record is that switch and the normal position renewal sub-district in the data in mobile phone of switch unit.Because the record in switching sequence can all not be the sub-district to take place switch and normal position new record more, so other write down and also can be used for carrying out path culculating, and other records can only position with base station location, and this bearing accuracy is lower than the switching bearing accuracy.Because base station range is big, to compare with switching the location, the location positioning vehicle ' through the base station is apart from existing than mistake.Therefore the accuracy of traffic information exists related with the event attribute of two switching points forming a switch unit.Using the initial termination of 1,2,3,4 expressions to write down in the actual computation respectively all is that switching is write down, switching is write down, initial termination record all is not that four kinds of affair characters are write down in switching for switching record, a termination are recorded as in a home record.
Velocity variations situation between the adjacent switch unit of percentage speed variation character representation.Generally speaking, acute variation can not take place in the adjacent period traffic behavior in highway section, so percentage speed variation can reflect the confidence level of data to a certain extent.
In addition; After handling through path culculating Vehicle Speed is demarcated on the chain of road (path between two switching points just obtains speed divided by the time interval); And because the adjustment of routing strategy and the characteristics of mobile phone mass data; Make in the processing cycle on same the road chain that (this is because the data in mobile phone amount is big to a plurality of velocity amplitudes of ubiquity; Article one, have a lot of data in mobile phone on the road, and a mobile phone switching sequence can match again on many roads, therefore have the velocity amplitude that a lot of groups of switching sequences obtain on same road).The purpose that merges based on the traffic information of svm classifier algorithm is the insincere problem that solves information on the same road chain that the routing strategy adjustment caused.
The data in mobile phone sample set that obtains behind the path culculating can be expressed as (xi, yi), i=1 wherein; 2 ..., n; X is switch unit attribute vector Rd, and d is the characteristic of division number, and yi belongs to {+1;-1} is through road chain speed and actual drive test speed being contrasted the key words sorting that obtains ,+1 expression valid data (the speed relative error is less than 30%) ,-1 expression invalid data (the speed relative error is greater than 30%).Observation through to data finds that the data in mobile phone sample is non-linear, in order to guarantee classification effectiveness, selects the polynomial kernel function that attribute space is mapped to a higher dimensional space, in this space, asks the optimal classification face, and the respective classified decision function is:
Wherein ai, bi are the optimization lineoid parameter that model training obtains, K (xi, x) expression polynomial kernel function; X is for treating the grouped data proper vector, and xi is a support vector, and yi is the support vector key words sorting; Sgn (x) is a decision function, and functional value is 1 when x＞0, otherwise is-1.
The traffic information fusion is that the traffic information that all vehicles on every road chain produce is done further fusion treatment, and generating with the road chain is the real-time dynamic information of unit, and the flow process that traffic information merges is as shown in Figure 6, comprising:
Because model supports vector quantity more (tens thousand of) makes classification speed slow, can't satisfy real-time calculation requirement.Present embodiment adopts a kind of quick svm classifier algorithm; Be about to use the svm classifier decision function of polynomial kernel function to expand into about treating the polynomial expression of each component of class vector; Divide time-like to obtain classification results through calculating each polynomial value; Make classified calculating amount and support vector quantity irrelevant, kept the information of whole support vectors simultaneously again.
Step 2036, calculate road conditions average velocity and hourage according to the valid data of preserving.
In a word, the above is merely preferred embodiment of the present invention, is not to be used to limit protection scope of the present invention.
Claims (10)
1. the real time acquiring method of a traffic information is characterized in that, comprising:
The radio data that traffic information calculates is not satisfied in deletion; Carry out path culculating, the driving path and the characteristic of division value that obtain according to path culculating are judged the validity of satisfying the need radio data chain calculating hourage; Valid data are merged, obtain traffic information.
2. traffic information real time acquiring method according to claim 1 is characterized in that, the step that the radio data of traffic information calculating is not satisfied in said deletion specifically comprises:
Deletion invalid data, non-moving data and non-vehicle-mounted data.
3. traffic information real time acquiring method according to claim 2 is characterized in that, the method for said deletion invalid data specifically comprises:
According to the radio data of the non-any active ues of mobile phone state in the deletion processing cycle, the base station location of affiliated base station does not cover the radio data of suburbs strategic road, and writes down the radio data that number is less than three mobile phone in a processing cycle.
4. according to claim 2 or 3 described traffic information real time acquiring methods, it is characterized in that the method for the non-moving data of said deletion specifically comprises:
Switched and the identical radio data of base station shifting coordinate the base station during deletion was conversed continuously.
5. traffic information real time acquiring method according to claim 4 is characterized in that, the method for the non-vehicle-mounted data of said deletion specifically comprises:
The mobile phone wireless mobile data that occurs loop in the deletion processing cycle in the switching sequence of base station.
6. traffic information real time acquiring method according to claim 5 is characterized in that, the step of said path culculating specifically comprises:
The grid at place is switched in the location, and obtains all highway sections in this grid;
With adding in the chain set of search road less than the highway section of predetermined threshold value with the switching position distance in the grid;
Judge whether next bar mobile phone wireless mobile data record switches, if, then with two base station shifting mid points as mobile phone location; Otherwise with base station location as mobile phone location;
In the set of search road chain, seek the coupling highway section, said coupling highway section drop on this highway section for the mobile phone location projection or with this highway section distance less than said predetermined threshold value.
7. traffic information real time acquiring method according to claim 6 is characterized in that, said path culculating further comprises the step of the characteristic of division value of obtaining SVMs SVM, and this step comprises:
When carrying out many couplings of path culculating output highway section result, be six types of characteristic of divisions of each coupling highway section output: data drift features, switching sequence integrity feature, timeliness characteristic, distance feature, event attribute characteristic and percentage speed variation characteristic.
8. traffic information real time acquiring method according to claim 7 is characterized in that, the acquisition methods of the characteristic of division value of said six types of characteristic of divisions comprises:
Said data drift features value is the average drift angle value in the switching sequence, and formula is:
Wherein DA is the average drift angle, DA
iThe switching sequence angle of respectively drifting about, DN is the number that drift takes place in the same switching sequence;
Said distance feature value is an operating range and road chain length switching point distance when;
Said switching sequence integrity feature value is to mate the ratio that accounts for the total number of records that successfully writes down in the switching sequence;
Said timeliness eigenwert is switching interval and the number of switching record;
Whether the incident in the mobile phone wireless mobile data that said event attribute eigenwert is a switch unit in the initial termination record is that switch the sub-district and the normal position is upgraded;
Said percentage speed variation eigenwert is the velocity variations situation between adjacent switch unit.
9. traffic information real time acquiring method according to claim 8 is characterized in that, saidly valid data are merged the step obtain traffic information specifically comprises:
A, read the svm classifier model that trains, calculate support vector polynomial expansion item value;
B, read the result of said path culculating, extract the characteristic of division vector, and characteristic of division is carried out standardization;
C, through the polynomial kernel function with the characteristic of division DUAL PROBLEMS OF VECTOR MAPPING to higher dimensional space, and calculate according to said support vector polynomial expansion item value and to treat the class vector classification results, if classification results greater than 0, is carried out next step; Otherwise this road chain information is saved as valid data, carry out next step;
D, judge whether in addition untreatment data, if, execution in step b; Otherwise carry out next step;
E, calculate road conditions average velocity and hourage according to the valid data of preserving.
10. traffic information real time acquiring method according to claim 9 is characterized in that, the said step that reads svm classifier Model Calculation support vector polynomial expansion item value specifically comprises:
Find the solution convex quadratic programming problem according to the classification samples that has identified category attribute and obtain the optimization lineoid, the training of svm classifier model is accomplished by support vector and optimization lineoid parametric representation in this plane;
The svm classifier decision function that uses the polynomial kernel function is expanded into about treating the polynomial expression of each component of class vector, divide time-like to obtain classification results through calculating each polynomial value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110412993.XA CN102496280B (en) | 2011-12-13 | 2011-12-13 | Method for obtaining road condition information in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110412993.XA CN102496280B (en) | 2011-12-13 | 2011-12-13 | Method for obtaining road condition information in real time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102496280A true CN102496280A (en) | 2012-06-13 |
| CN102496280B CN102496280B (en) | 2014-04-23 |
Family
ID=46188099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110412993.XA Expired - Fee Related CN102496280B (en) | 2011-12-13 | 2011-12-13 | Method for obtaining road condition information in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102496280B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722984A (en) * | 2012-06-19 | 2012-10-10 | 张家港市鸿嘉数字科技有限公司 | Real-time road condition monitoring method |
| CN103544837A (en) * | 2012-07-09 | 2014-01-29 | 财团法人工业技术研究院 | Traffic information estimation method and system combining cross-regional position updating and communication |
| CN104021680A (en) * | 2014-06-18 | 2014-09-03 | 兴天通讯技术（天津）有限公司 | Traffic flow prediction method and system based on mobile terminals |
| CN104200667A (en) * | 2014-09-19 | 2014-12-10 | 上海美慧软件有限公司 | Traffic jam grade detection method based on cellphone signal data |
| CN105243844A (en) * | 2015-10-14 | 2016-01-13 | 华南理工大学 | Road state identification method based on mobile phone signal |
| CN105702041A (en) * | 2016-04-21 | 2016-06-22 | 东南大学 | Highway multisource data fusion state estimation system based on neural network and method thereof |
| CN106408936A (en) * | 2016-07-28 | 2017-02-15 | 东南大学 | Mobile-phone-data-based real-time detection method for abnormal event of highway |
| CN106611495A (en) * | 2015-10-27 | 2017-05-03 | 北京航天长峰科技工业集团有限公司 | Comprehensive traffic flow monitoring method based on real-time floating vehicle data |
| CN106710208A (en) * | 2015-11-16 | 2017-05-24 | 中兴通讯股份有限公司 | Traffic state acquisition method and device |
| CN107463940A (en) * | 2017-06-29 | 2017-12-12 | 清华大学 | Vehicle type recognition method and apparatus based on data in mobile phone |
| CN107644533A (en) * | 2017-10-27 | 2018-01-30 | 上海云砥信息科技有限公司 | The virtual section wagon flow quantity monitoring method of highway based on mobile network data |
| TWI615814B (en) * | 2017-04-06 | 2018-02-21 | Zeng Ming De | Mobile device location grouping, time system grouping and method of generating traffic time planning using big data |
| CN108288377A (en) * | 2017-01-09 | 2018-07-17 | 腾讯科技（深圳）有限公司 | A kind of generation method and device of traffic information |
| CN109003453A (en) * | 2018-08-30 | 2018-12-14 | 中国人民解放军国防科技大学 | Floating car section average speed short-term prediction method based on support vector machine |
| CN110111563A (en) * | 2019-04-08 | 2019-08-09 | 东南大学 | A kind of real-time traffic states estimation method of city expressway |
| CN110175654A (en) * | 2019-05-29 | 2019-08-27 | 广州小鹏汽车科技有限公司 | A kind of update method and system of track road sign |
| CN110708664A (en) * | 2019-10-11 | 2020-01-17 | 同帅科技（天津）有限公司 | Traffic flow sensing method and device, computer storage medium and electronic equipment |
| CN110827540A (en) * | 2019-11-04 | 2020-02-21 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN110954115A (en) * | 2018-09-26 | 2020-04-03 | 上海擎感智能科技有限公司 | Route key information generation method and device |
| CN111161529A (en) * | 2018-10-18 | 2020-05-15 | 中华电信股份有限公司 | Artificial intelligent traffic flow estimation system and method using mobile network signaling data |
| CN111402575A (en) * | 2018-12-17 | 2020-07-10 | 中国移动通信集团北京有限公司 | Method and device for evaluating traffic running state |
| CN111859291A (en) * | 2020-06-23 | 2020-10-30 | 北京百度网讯科技有限公司 | Traffic accident recognition method, device, equipment and computer storage medium |
| TWI719640B (en) * | 2019-09-17 | 2021-02-21 | 中華電信股份有限公司 | Method and system for detecting traffic events |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008111913A1 (en) * | 2007-03-15 | 2008-09-18 | Agis Pte Ltd | A method for location determination and a mobile device |
| WO2008118597A1 (en) * | 2007-03-27 | 2008-10-02 | Gm Global Technology Operations, Inc. | Traffic data collection utilizing a cellular communication network and probe units |
| CN102081851A (en) * | 2009-11-30 | 2011-06-01 | 国际商业机器公司 | Method and device for determining passing speed of road based on mobile communication network |
-
2011
- 2011-12-13 CN CN201110412993.XA patent/CN102496280B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008111913A1 (en) * | 2007-03-15 | 2008-09-18 | Agis Pte Ltd | A method for location determination and a mobile device |
| WO2008118597A1 (en) * | 2007-03-27 | 2008-10-02 | Gm Global Technology Operations, Inc. | Traffic data collection utilizing a cellular communication network and probe units |
| CN102081851A (en) * | 2009-11-30 | 2011-06-01 | 国际商业机器公司 | Method and device for determining passing speed of road based on mobile communication network |
Non-Patent Citations (2)
| Title |
|---|
| 冯冲等: "基于时空关系的手机定位数据处理方法", 《贵州大学学报（自然科学版）》, vol. 28, no. 3, 30 June 2011 (2011-06-30) * |
| 杨飞等: "基于手机切换定位的交通路网标定方法", 《同济大学学报（自然科学版）》, vol. 37, no. 1, 31 January 2009 (2009-01-31) * |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722984B (en) * | 2012-06-19 | 2015-01-28 | 张家港市鸿嘉数字科技有限公司 | Real-time road condition monitoring method |
| CN102722984A (en) * | 2012-06-19 | 2012-10-10 | 张家港市鸿嘉数字科技有限公司 | Real-time road condition monitoring method |
| CN103544837A (en) * | 2012-07-09 | 2014-01-29 | 财团法人工业技术研究院 | Traffic information estimation method and system combining cross-regional position updating and communication |
| CN103544837B (en) * | 2012-07-09 | 2017-03-01 | 财团法人工业技术研究院 | Traffic information estimation method and system combining cross-regional position updating and communication |
| CN104021680A (en) * | 2014-06-18 | 2014-09-03 | 兴天通讯技术（天津）有限公司 | Traffic flow prediction method and system based on mobile terminals |
| CN104200667A (en) * | 2014-09-19 | 2014-12-10 | 上海美慧软件有限公司 | Traffic jam grade detection method based on cellphone signal data |
| CN104200667B (en) * | 2014-09-19 | 2016-07-27 | 上海美慧软件有限公司 | A kind of traffic congestion hierarchical detection method based on mobile phone signal data |
| CN105243844A (en) * | 2015-10-14 | 2016-01-13 | 华南理工大学 | Road state identification method based on mobile phone signal |
| CN106611495A (en) * | 2015-10-27 | 2017-05-03 | 北京航天长峰科技工业集团有限公司 | Comprehensive traffic flow monitoring method based on real-time floating vehicle data |
| CN106710208A (en) * | 2015-11-16 | 2017-05-24 | 中兴通讯股份有限公司 | Traffic state acquisition method and device |
| CN105702041A (en) * | 2016-04-21 | 2016-06-22 | 东南大学 | Highway multisource data fusion state estimation system based on neural network and method thereof |
| CN106408936B (en) * | 2016-07-28 | 2018-11-16 | 东南大学 | A kind of highway anomalous event real-time detection method based on data in mobile phone |
| CN106408936A (en) * | 2016-07-28 | 2017-02-15 | 东南大学 | Mobile-phone-data-based real-time detection method for abnormal event of highway |
| CN108288377A (en) * | 2017-01-09 | 2018-07-17 | 腾讯科技（深圳）有限公司 | A kind of generation method and device of traffic information |
| TWI615814B (en) * | 2017-04-06 | 2018-02-21 | Zeng Ming De | Mobile device location grouping, time system grouping and method of generating traffic time planning using big data |
| CN107463940B (en) * | 2017-06-29 | 2020-02-21 | 清华大学 | Vehicle type identification method and device based on mobile phone data |
| CN107463940A (en) * | 2017-06-29 | 2017-12-12 | 清华大学 | Vehicle type recognition method and apparatus based on data in mobile phone |
| CN107644533A (en) * | 2017-10-27 | 2018-01-30 | 上海云砥信息科技有限公司 | The virtual section wagon flow quantity monitoring method of highway based on mobile network data |
| CN109003453A (en) * | 2018-08-30 | 2018-12-14 | 中国人民解放军国防科技大学 | Floating car section average speed short-term prediction method based on support vector machine |
| CN109003453B (en) * | 2018-08-30 | 2020-05-22 | 中国人民解放军国防科技大学 | Floating car section average speed short-term prediction method based on support vector machine |
| CN110954115A (en) * | 2018-09-26 | 2020-04-03 | 上海擎感智能科技有限公司 | Route key information generation method and device |
| CN111161529A (en) * | 2018-10-18 | 2020-05-15 | 中华电信股份有限公司 | Artificial intelligent traffic flow estimation system and method using mobile network signaling data |
| CN111161529B (en) * | 2018-10-18 | 2021-06-08 | 中华电信股份有限公司 | Artificial intelligent traffic flow estimation system and method using mobile network signaling data |
| CN111402575A (en) * | 2018-12-17 | 2020-07-10 | 中国移动通信集团北京有限公司 | Method and device for evaluating traffic running state |
| CN110111563A (en) * | 2019-04-08 | 2019-08-09 | 东南大学 | A kind of real-time traffic states estimation method of city expressway |
| CN110175654A (en) * | 2019-05-29 | 2019-08-27 | 广州小鹏汽车科技有限公司 | A kind of update method and system of track road sign |
| CN110175654B (en) * | 2019-05-29 | 2021-06-01 | 广州小鹏自动驾驶科技有限公司 | Method and system for updating track signposts |
| TWI719640B (en) * | 2019-09-17 | 2021-02-21 | 中華電信股份有限公司 | Method and system for detecting traffic events |
| CN110708664A (en) * | 2019-10-11 | 2020-01-17 | 同帅科技（天津）有限公司 | Traffic flow sensing method and device, computer storage medium and electronic equipment |
| CN110827540A (en) * | 2019-11-04 | 2020-02-21 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN110827540B (en) * | 2019-11-04 | 2021-03-12 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN111859291A (en) * | 2020-06-23 | 2020-10-30 | 北京百度网讯科技有限公司 | Traffic accident recognition method, device, equipment and computer storage medium |
| US11328600B2 (en) | 2020-06-23 | 2022-05-10 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for identifying traffic accident, device and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102496280B (en) | 2014-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102496280B (en) | Method for obtaining road condition information in real time | |
| Zhao et al. | Travel time prediction: Based on gated recurrent unit method and data fusion | |
| Lin et al. | A review of travel-time prediction in transport and logistics | |
| Edie | Car-following and steady-state theory for noncongested traffic | |
| CN104050817B (en) | Speed limiting information base generation and speed limiting information detection method and system | |
| CN105261212B (en) | A kind of trip space-time analysis method based on GPS data from taxi map match | |
| CN105138779A (en) | Vehicle-mounted GPS space-time trajectory big data optimization method and system | |
| CN107657637A (en) | A kind of agricultural machinery working area acquisition methods | |
| CN111612670B (en) | Method, device and computer equipment for constructing emission list of motor vehicle | |
| CN102968900B (en) | Method for processing RFID (Radio Frequency Identification) traffic data | |
| CN104778834A (en) | Urban road traffic jam judging method based on vehicle GPS data | |
| CN109859495A (en) | A method of overall travel speed is obtained based on RFID data | |
| Pan et al. | Forecasting spatiotemporal impact of traffic incidents for next-generation navigation systems | |
| CN108765961A (en) | A kind of floating car data processing method based on modified amplitude limit average filter | |
| Astarita et al. | A review of traffic signal control methods and experiments based on Floating Car Data (FCD) | |
| CN109587622B (en) | Intersection steering flow analysis system and method based on base station signaling data | |
| Zong et al. | Bus-Car Mode Identification: Traffic Condition–Based Random-Forests Method | |
| CN106408936A (en) | Mobile-phone-data-based real-time detection method for abnormal event of highway | |
| CN102156909A (en) | Method for identifying rail transit trip mode based on mobile phone signal data | |
| Li et al. | A simulation approach to detect arterial traffic congestion using cellular data | |
| CN102542617A (en) | Path identification station arranging method of complicated road net | |
| Zhao et al. | Travel time prediction based on pattern matching method | |
| Abbas et al. | Evaluation of the use of streaming graph processing algorithms for road congestion detection | |
| Gashaw et al. | Lagrangian formulation for mixed traffic flow including two-wheelers | |
| Oskarbski et al. | Multi-level transport systems model for traffic management activities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20161012 Address after: 18, building 1006, block C, Shenzhen International Innovation Center, No. 518033 Shennan Road, Shenzhen, Guangdong, Futian District Patentee after: Shenzhen Air Technology Co., Ltd. Address before: 100191 Haidian District, Xueyuan Road, No. 37, Patentee before: Beihang University |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140423 Termination date: 20171213 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |